INDEX

Explanations

references to simplicity or straightforwardness in explanations or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĢÑĥÑģ

-0.15

-0.14

issing

-0.14

å§ĭ

-0.14

rush

-0.14

/cpu

-0.14

Ð»ÐµÐº

-0.14

raphic

-0.13

.docker

-0.13

aname

-0.13

POSITIVE LOGITS

tons

0.27

ton

0.25

/simple

0.22

/plain

0.20

mente

0.18

 straightforward

0.18

tron

0.17

xes

0.17

-minded

0.17

st

0.17

Activations Density 0.031%

references to simplicity or straightforwardness in explanations or concepts

No Comments

No Known Activations